编写一个简单的Java程序,实现从HDFS中读取文件并计算文件中单词的数量。
时间: 2024-03-16 09:46:22 浏览: 69
好的,以下是一个简单的Java程序,实现从HDFS中读取文件并计算文件中单词的数量:
```
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class WordCount {
public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>{
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
}
}
}
public static class IntSumReducer extends Reducer<Text,IntWritable,Text,IntWritable> {
private IntWritable result = new IntWritable();
public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
FileSystem fs = FileSystem.get(conf);
if (args.length < 2) {
System.err.println("Usage: WordCount <input path> <output path>");
System.exit(-1);
}
Job job = Job.getInstance(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
// 设置输入路径和输出路径
FileInputFormat.addInputPath(job, new Path(args[0]));
Path outputPath = new Path(args[1]);
if (fs.exists(outputPath)) {
fs.delete(outputPath, true);
}
FileOutputFormat.setOutputPath(job, outputPath);
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
```
在执行时,需要指定输入路径和输出路径,例如:
```
hadoop jar wordcount.jar WordCount /input/sample.txt /output
```
其中,/input/sample.txt表示输入文件的路径,/output表示输出路径。
阅读全文